© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 7172
    Prev
    Next
    INDEX
    Explanations

    rankings or positions related to military or organizational structures

    oai_token-act-pair · gpt-3.5-turbo

    references to different ranks or titles within military or organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dos
    -0.75
    izon
    -0.72
    âĶģ
    -0.70
    Ti
    -0.68
    tera
    -0.66
    rise
    -0.66
    gp
    -0.65
     Timber
    -0.64
    creen
    -0.64
    MED
    -0.63
    POSITIVE LOGITS
     corps
    0.97
     officer
    0.89
    ially
    0.86
    utenant
    0.84
    geant
    0.77
    士
    0.77
     officers
    0.77
     colonel
    0.76
     emer
    0.74
    holder
    0.69
    Activations Density 0.034%

    No Known Activations